Re: Doubt in pgbench TPS number
От | Fabien COELHO |
---|---|
Тема | Re: Doubt in pgbench TPS number |
Дата | |
Msg-id | alpine.DEB.2.10.1509250712330.21900@sto обсуждение исходный текст |
Ответ на | Doubt in pgbench TPS number (Tatsuo Ishii <ishii@postgresql.org>) |
Ответы |
Re: Doubt in pgbench TPS number
|
Список | pgsql-hackers |
Hello Tatsuo-san, > $ pgbench -C -n -p 11002 -c 10 -T 30 -f test.sql test > tps = 95.799114 (including connections establishing) > tps = 124.487149 (excluding connections establishing) > > Interesting thing is, the number from "excluding connections > establishing". 124.487149 tps means 0.008032 seconds per > transaction. Since the query executes pg_sleep(0.1), I think the > number should be equal to or greater than 0.1. Maybe a tolerance, but > 20% of error seems to be too high for me. Indeed. > Note that if "-C" does not present, the TPS number seems to be sane. Hmmm... I never use -C. The formula seems ok: tps_exclude = normal_xacts / (time_include - (INSTR_TIME_GET_DOUBLE(conn_total_time) / nthreads)); conn_total_time is the cumulated time spent by all threads. A quick look at the logic reveals some minor issues (conn_time is passed as an argument to doCustom, although it is already available as a "thread" field, stange). I spotted "threads" used instead of "thread" in an accumulation, but it is not related to this computation. Hmmm. I'll have a slower look... -- Fabien.
В списке pgsql-hackers по дате отправления: